GET
/v1/schemas/fal/audio/elevenlabs/music/v2
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace29f3a9f3b72ec3f0c900eed79cf5ceaea512f2a14519f4dcce220c9042ae65a0{
"fetchedAt": 1794114001,
"extractorVersion": "2",
"verifiedAt": null
} |
Request body
7 properties · 0 required · 3 $defs| property | type | description | constraints |
|---|---|---|---|
| enable_safety_checker | boolean | Check input content for safety. Disabling requires account authorization. | default: true |
| composition_plan | MusicV2CompositionPlan | The chunk-based composition plan for the music | nullable |
| music_length_ms | integer | The length of the song to generate in milliseconds. Used only in conjunction with prompt. Must be between 3000ms and 600000ms. Optional - if not provided, the model will choose a length based on the prompt. | 3000 ≤ n ≤ 600000 · nullable |
| output_format | enum | Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for T… | mp3_22050_32 | mp3_24000_48 | mp3_44100_32 | mp3_44100_64 | mp3_44100_96 | mp3_44100_128 · +19 more · default: "mp3_48000_192" |
| force_instrumental | boolean | If true, guarantees that the generated song will be instrumental. If false, the song may or may not be instrumental depending on the prompt. Can only be used with prompt. | default: false |
| seed | integer | Random seed to initialize the music generation process. Can only be used with composition_plan. The same seed with the same parameters gives more consistent results, but exact reproducibility is not guaranteed. | nullable |
| prompt | string | The text prompt describing the music to generate | length ≤ 4100 · nullable |
Types
3 $defsMusicAudioReferenceobject
An audio clip whose style conditions a ``music_v2`` / ``music_v2.5`` chunk.
| strength | enum | How strongly the model follows the reference. Low lets it deviate and be more creative, high keeps it close to the reference. | low | medium | high | xhigh · nullable |
| audio_url* | string | URL of the audio clip to use as the style reference. | |
| end_ms | integer | Offset into the clip where the referenced window ends, in milliseconds. Defaults to 30000ms after start_ms, or the end of the clip if it is shorter. The window must be at most 30000ms long. | n > 0 · nullable |
| start_ms | integer | Offset into the clip where the referenced window starts, in milliseconds. | n ≥ 0 · default: 0 |
MusicGenerationChunkobject
One generation chunk of a ``music_v2`` / ``music_v2.5`` composition plan.
| audio_reference | MusicAudioReference | An audio clip whose style conditions a ``music_v2`` / ``music_v2.5`` chunk. | nullable |
| context_adherence | enum | How closely this chunk follows the context of its surrounding chunks. Low adherence lets the model deviate and be more creative, high adherence keeps it consistent with the surrounding context. | low | medium | high · nullable |
| positive_styles* | string[] | The styles and musical directions that should be present in this chunk. Use English for best results. The styles of the first chunk matter most as they set the overall tone and genre; later chunks can add nuance, progression or change direction. | |
| duration_ms* | integer | The duration of the chunk in milliseconds. Must be between 3000ms and 120000ms. | 3000 ≤ n ≤ 120000 |
| text* | string | The text to generate for this chunk. Can start with an optional section name in square brackets, e.g. [Verse 1], followed by lyric lines, plus inline directions in curly braces, e.g. {scratching}. Section names must be between 1 and 100 characters. At most 30 … | |
| negative_styles | string[] | The styles and musical directions that should not be present in this chunk. Leaving this empty is a good default; only set it to explicitly avoid a particular style or direction. | nullable |
MusicV2CompositionPlanobject
| chunks* | MusicGenerationChunk[] | The chunks that make up the generation, in order. At most 30 chunks, totalling between 3000ms and 600000ms. | items ≥ 1 · items ≤ 30 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"elevenlabs/music/v2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}